An image based approach to detect Retinopathy of prematurity

In this paper, an automatic method is proposed to detect Retinopathy of prematurity (ROP) in premature infants. ROP is an ocular disease of low birth weight infants and it can cause blindness. It is essential that those caring for premature infants know who is at risk of ROP, when screening must begin and how often these infants need to be examined. So, ROP detection is necessary for both screening the pathology and follow up (progression measurement). Automating this task, which is currently performed manually, would bring more objectivity and reproducibility. We proposed image processing algorithms such as histogram equalization methods, feature extraction, measuring curvature by changes in intensity and template matching. A simple matched filter is proposed to roughly match the direction of vessels. The retinal vessels are segmented using a spacek operator, simple and standard 2-D Gaussian matched filter. Segmented vessels are thinned, smoothened and filtered using local intensity. Automatic screening will entail several advantages, like a substantial reduction in the workload of clinicians, improving the sensitivity of the test and a better accuracy in diagnosis. The effectiveness of the proposed method has been verified through machine vision techniques and the results obtained are encouraged by experts.